A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[CI] remove flaky v0 test (#22864)
Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
Robert Shaw committed
Aug 14, 2025 at 00:41 UTC
a353bd083d22c92c90479d6b5b5029c0daed49da
1 file changed
+1
-12
tests/entrypoints/openai/test_default_mm_loras.py
+1
-12
@@ -24,18 +24,7 @@ ACTIVE_MM_LORA_RESPONSE = "Spoken text: The first words I spoke in the original
24
25
26
@pytest.fixture(scope="module")
27
-def monkeypatch_module():
28
- from _pytest.monkeypatch import MonkeyPatch
29
- mpatch = MonkeyPatch()
30
- yield mpatch
31
- mpatch.undo()
32
-
33
-
34
-@pytest.fixture(scope="module", params=[False, True])
35
-def multimodal_server(request, monkeypatch_module): # noqa: F811
36
-
37
- use_v1 = request.param
38
- monkeypatch_module.setenv('VLLM_USE_V1', '1' if use_v1 else '0')
27
+def multimodal_server(): # noqa: F811
28
29
args = [
30
# use half precision for speed and memory savings in CI environment